Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2504.12605 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909582257815552 |
|---|---|
| author | Su, Xin Wu, Chen Zhang, Yu Lyu, Chen Zheng, Zhuoran |
| author_facet | Su, Xin Wu, Chen Zhang, Yu Lyu, Chen Zheng, Zhuoran |
| contents | Restoring images afflicted by complex real-world degradations remains challenging, as conventional methods often fail to adapt to the unique mixture and severity of artifacts present. This stems from a reliance on indirect cues which poorly capture the true perceptual quality deficit. To address this fundamental limitation, we introduce AdaQual-Diff, a diffusion-based framework that integrates perceptual quality assessment directly into the generative restoration process. Our approach establishes a mathematical relationship between regional quality scores from DeQAScore and optimal guidance complexity, implemented through an Adaptive Quality Prompting mechanism. This mechanism systematically modulates prompt structure according to measured degradation severity: regions with lower perceptual quality receive computationally intensive, structurally complex prompts with precise restoration directives, while higher quality regions receive minimal prompts focused on preservation rather than intervention. The technical core of our method lies in the dynamic allocation of computational resources proportional to degradation severity, creating a spatially-varying guidance field that directs the diffusion process with mathematical precision. By combining this quality-guided approach with content-specific conditioning, our framework achieves fine-grained control over regional restoration intensity without requiring additional parameters or inference iterations. Experimental results demonstrate that AdaQual-Diff achieves visually superior restorations across diverse synthetic and real-world datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_12605 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AdaQual-Diff: Diffusion-Based Image Restoration via Adaptive Quality Prompting Su, Xin Wu, Chen Zhang, Yu Lyu, Chen Zheng, Zhuoran Computer Vision and Pattern Recognition Restoring images afflicted by complex real-world degradations remains challenging, as conventional methods often fail to adapt to the unique mixture and severity of artifacts present. This stems from a reliance on indirect cues which poorly capture the true perceptual quality deficit. To address this fundamental limitation, we introduce AdaQual-Diff, a diffusion-based framework that integrates perceptual quality assessment directly into the generative restoration process. Our approach establishes a mathematical relationship between regional quality scores from DeQAScore and optimal guidance complexity, implemented through an Adaptive Quality Prompting mechanism. This mechanism systematically modulates prompt structure according to measured degradation severity: regions with lower perceptual quality receive computationally intensive, structurally complex prompts with precise restoration directives, while higher quality regions receive minimal prompts focused on preservation rather than intervention. The technical core of our method lies in the dynamic allocation of computational resources proportional to degradation severity, creating a spatially-varying guidance field that directs the diffusion process with mathematical precision. By combining this quality-guided approach with content-specific conditioning, our framework achieves fine-grained control over regional restoration intensity without requiring additional parameters or inference iterations. Experimental results demonstrate that AdaQual-Diff achieves visually superior restorations across diverse synthetic and real-world datasets. |
| title | AdaQual-Diff: Diffusion-Based Image Restoration via Adaptive Quality Prompting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.12605 |